Saliency detection is a fundamental and challenging task in computer vision, which aims at distinguishing the most conspicuous objects or regions in an image. Existing deep-learning methods mainly rely on the entire image to learn the global context information for saliency detection, which loses the spatial relation and results in ambiguity in predicting saliency maps. In this paper, we propose a novel deep sub-region network (DSR-Net) equipped with a sequence of sub-region dilated blocks (SRDB) by aggregating multi-scale salient context information of multiple sub-regions, such that the global context information from the whole image and local contexts from sub-regions are fused together, making the saliency prediction more accurate. Our SRDB separates the input feature map at different layers of a convolutional neural network (CNN) into different sub-regions and then designs a parallel ASPP module to refine feature maps at each sub-region. Experiments on the five widely-used saliency benchmark datasets demonstrate that our network outperforms recent state-of-the-art saliency detectors quantitatively and qualitatively on all the benchmarks.

中文翻译：

---

用于显着目标检测的深度子区域网络

显着性检测是计算机视觉中一项基本且具有挑战性的任务，旨在区分图像中最显着的对象或区域。现有的深度学习方法主要依靠整幅图像学习全局上下文信息进行显着性检测，失去了空间关系，导致显着性图预测模糊。在本文中，我们通过聚合多个子区域的多尺度显着上下文信息，提出了一种配备一系列子区域扩张块（SRDB）的新型深度子区域网络（DSR-Net），使得全局上下文来自整个图像的信息和来自子区域的局部上下文融合在一起，使显着性预测更加准确。我们的 SRDB 将卷积神经网络 (CNN) 不同层的输入特征图分成不同的子区域，然后设计一个并行的 ASPP 模块来细化每个子区域的特征图。在五个广泛使用的显着性基准数据集上进行的实验表明，我们的网络在所有基准上在数量和质量上都优于最近最先进的显着性检测器。